Name: newslit
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

newslit

Newslit integration. Manage Organizations. Use when the user wants to interact with Newslit data.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/newslit/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, largely executable integration guide with a strong connection-state feedback loop, but it carries opening fluff, redundant command listings, a broken "Step 2" reference, and no real Newslit action example. Tightening prose and fixing the step cross-reference would notably improve it.

Suggestions

Remove the audience padding in the opening paragraph ("It is used by communications teams...") and drop the redundant action-list command in "Popular actions" since it duplicates "Searching for actions".

Fix the "skip to Step 2" reference by labeling the next step (e.g., add a "## Step 2: Search for actions" header) so the cross-reference resolves.

Add one end-to-end example with a real Newslit action (e.g., searching articles by query) and a brief output/error-handling check after `membrane action run` to add a validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The guide is mostly efficient with concrete commands, but the opening paragraph pads with audience fluff ("It is used by communications teams, marketing departments, and public relations agencies") and the "Popular actions" section re-lists the action-list command already shown, fitting score 3 (mostly efficient, some unnecessary explanation); it is tighter than score 2 but not clean enough for score 4.	3 / 5
Actionability	Concrete, copy-paste bash commands with flags and a full proxy flag table make the guidance mostly executable, matching score 4; it stays below 5 because only generic placeholders ("QUERY", "<actionId>") appear and no real Newslit action example (e.g., searching articles) is shown for the common cases.	4 / 5
Workflow Clarity	A clear install-authenticate-connect-search-run sequence includes a genuine feedback loop on connection state (poll READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR with re-polling), reaching score 4; it is capped below 5 because "skip to Step 2" references a non-existent Step 2 and the action-run step has no validation or error-handling checkpoint.	4 / 5
Progressive Disclosure	No bundle files exist and the single-file body is well-organized into clearly headed sections, fitting score 4 (good structure, most content appropriately placed, minor gaps); it does not reach 5 because the ~140-line guide inlines reference-style material (the clientAction schema and proxy flag table) and has minor redundancy between "Searching for actions" and "Popular actions".	4 / 5
	Total	15 / 20 Passed

Description

62%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description correctly pairs a what-statement with an explicit Use-when trigger and leverages a distinctive brand name, but its capability list is thin (only "Manage Organizations") and its trigger phrasing is broad. Expanding both would lift specificity and trigger-term quality.

Suggestions

Add 2-3 concrete Newslit actions to the what-statement (e.g., search articles, list sources, manage collections) instead of only "Manage Organizations".

Broaden the when-trigger with natural variations a user might say, such as "monitor news coverage", "track media mentions", or "search Newslit articles".

Align the description's named entity ("Organizations") with the entities the body actually exposes (Article, Tag, Source, User, Collection, Search) to avoid mismatched expectations.

Dimension	Reasoning	Score
Specificity	"Manage Organizations" names the domain plus a single concrete action, matching the score-3 anchor (domain and 1-2 concrete actions, not comprehensive); it lists only one action, so it is below score 4, while that action is concrete enough to exceed score 2's generic-minimal bar.	3 / 5
Completeness	It answers both "what" ("Newslit integration. Manage Organizations.") and "when" with an explicit "Use when the user wants to interact with Newslit data" clause, satisfying the score-4 anchor (both present, when could be more specific); the when-trigger is generic rather than listing concrete trigger phrases, so it stops below score 5.	4 / 5
Trigger Term Quality	"Newslit" and "Newslit data" are specific natural keywords a user would say, but no synonyms or variations are offered, fitting score 3 (some relevant keywords, missing common variations); the brand term is concrete enough to clear score 2 but coverage is too thin for score 4.	3 / 5
Distinctiveness Conflict Risk	"Newslit" is a distinct named platform giving it a clear niche with minimal conflict risk, but the broad "interact with Newslit data" trigger and generic "Manage Organizations" action introduce minor overlap risk, placing it at score 4 rather than 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/newslit/SKILL.md
Commit: f484c82

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.